WO2017028012A1 - 交通拥堵状况检测装置及方法 - Google Patents
交通拥堵状况检测装置及方法 Download PDFInfo
- Publication number
- WO2017028012A1 WO2017028012A1 PCT/CN2015/086967 CN2015086967W WO2017028012A1 WO 2017028012 A1 WO2017028012 A1 WO 2017028012A1 CN 2015086967 W CN2015086967 W CN 2015086967W WO 2017028012 A1 WO2017028012 A1 WO 2017028012A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- foreground
- pixels
- image
- input image
- predetermined area
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
Definitions
- the present invention relates to the field of information technology, and in particular, to a traffic congestion condition detecting apparatus and method.
- edge detection and counting methods are usually used to detect traffic congestion conditions.
- the edge detection method detects the congestion state by the number of edge pixels
- the counting method detects the congestion state by the number of vehicles passing through the monitoring area per unit time.
- the inventors have found that when the existing edge detection method is used to detect the traffic congestion condition, the edge of the road is detected not only by detecting the edge of the vehicle, but also the detection result is inaccurate.
- the method needs to be based on time. The parameters are adjusted frequently with location; when the existing counting method is used to detect traffic congestion, the detection result is not accurate.
- Embodiments of the present invention provide a traffic congestion condition detecting apparatus and method, which calculate a congestion index according to the number of foreground pixels of a foreground image in a predetermined area and the number of pixels of an input image, thereby detecting a traffic congestion condition, and capable of performing accurate real-time detection. Good stickiness and strong noise tolerance.
- a traffic congestion condition detecting apparatus comprising: an extracting unit configured to extract a foreground image from an input image according to a background model; and a calculating unit, wherein the calculating unit is configured to: Calculating a congestion index according to a number of foreground pixels of the foreground image in a predetermined area and a number of pixels of the input image in the predetermined area; a detecting unit, configured to use the congestion according to the congestion Index to detect traffic congestion
- a traffic congestion condition detecting method includes: extracting a foreground image from an input image according to a background model; and determining a number of foreground pixels in the predetermined area according to the foreground image and the input image A congestion index is calculated in the number of pixels in the predetermined area; and a traffic congestion condition is detected according to the congestion index.
- the beneficial effects of the embodiments of the present invention are: calculating the congestion index according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, enabling accurate real-time detection, and having good robustness and having Strong noise tolerance.
- FIG. 1 is a schematic structural diagram of a traffic congestion state detecting apparatus according to an embodiment of the present invention
- FIG. 2 is a schematic structural diagram of a correction unit 104 according to an embodiment of the present invention.
- FIG. 3 is a schematic structural diagram of a processing unit 105 according to an embodiment of the present invention.
- FIG. 4 is a schematic structural diagram of an electronic device according to Embodiment 2 of the present invention.
- Figure 5 is a schematic block diagram showing the system configuration of an electronic device according to Embodiment 2 of the present invention.
- FIG. 6 is a flowchart of a method for detecting a traffic congestion condition according to Embodiment 3 of the present invention.
- Fig. 7 is a flow chart showing a method of detecting a traffic congestion condition according to a fourth embodiment of the present invention.
- Embodiments of the present invention provide a traffic congestion condition detecting apparatus.
- 1 is a schematic structural diagram of a traffic congestion condition detecting apparatus according to an embodiment of the present invention. As shown in FIG. 1, the apparatus 100 includes:
- the extracting unit 101 is configured to extract a foreground image from the input image according to the background model
- the calculating unit 102 is configured to calculate a congestion index according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image in the predetermined area;
- the detecting unit 103 is configured to detect a traffic congestion condition according to the congestion index.
- the congestion index is calculated according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, and accurate real-time detection can be performed, which is robust and has strong robustness. Noise tolerance.
- the input image can be obtained according to an existing method.
- the input image can be obtained by extracting a certain frame image in the surveillance video, for example, the input image is the current frame.
- the surveillance video can be obtained by installing a camera above the area that needs to be monitored.
- the background model may use any background model capable of detecting objects moving slowly or stationary for a certain period of time, and embodiments of the present invention do not limit the specific background model.
- the extracting unit 101 extracts the foreground image from the input image according to the background model, for example, by comparing the background model and the input image, and setting the pixel value of the distinct pixel to 1, the pixel is the foreground pixel. .
- the foreground image may be a binarized image, wherein the foreground pixel has a pixel value of 1, and the remaining pixels have a pixel value of zero.
- the computing unit 102 after extracting the foreground image, the computing unit 102 is in the predetermined area according to the foreground image.
- the congestion index is calculated by the number of foreground pixels in the middle and the number of pixels of the input image in the predetermined area.
- the predetermined area may be set according to actual needs, for example, the predetermined area is a Region of Interest (ROI).
- ROI Region of Interest
- the calculation unit 102 may calculate the congestion index based on the relationship between the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image in the predetermined area.
- the congestion index may be calculated based on various proportional relationships of the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image in the predetermined area. Among them, the number of pixels can be obtained by counting.
- the computing unit 102 can calculate the congestion index according to the following formula (1):
- J represents the congestion index
- F represents the number of foreground pixels of the foreground image in the predetermined area
- N represents the number of pixels of the input image in the predetermined area
- F, N are positive integers.
- the detecting unit 103 detects the traffic congestion condition based on the congestion index.
- the current congestion condition can be determined based on the magnitude relationship between the value of the congestion index J and the predetermined threshold.
- the predetermined threshold may be set according to actual needs.
- the congestion index J is calculated using the above formula (1), the value of J is between 0 and 1, and when the congestion index J is greater than 0.8, the current traffic is judged to be heavily congested, when the congestion index J When it is between 0.6 and 0.8, it is judged that the current traffic is moderately congested. When the congestion index J is between 0.4 and 0.6, it is judged that the current traffic is lightly congested, and when the congestion index J is less than 0.4, Judging that the current traffic is smooth.
- the apparatus 100 may further include:
- the correcting unit 104 is configured to correct the input image and provide the corrected image to the extracting unit 101 for extracting the foreground image from the corrected input image according to the background model.
- correction unit 104 is an optional component, which is indicated by a dashed box in FIG.
- FIG. 2 is a schematic structural diagram of a correction unit 104 according to an embodiment of the present invention. As shown in FIG. 2, the correction unit 104 includes:
- the first correcting unit 201 is configured to correct a graphic of a road in the input image.
- the image of the road in the input image may be distorted due to the problem of the shooting angle and the distance.
- a road that is originally rectangular may appear trapezoidal in the input image due to the problem of the shooting angle.
- the first correcting unit 201 corrects the trapezoidal road image to a rectangle.
- the accuracy of the detection can be further improved by correcting the input image.
- the apparatus 100 may further include:
- the processing unit 105 is configured to perform morphological processing on the foreground image, and provide the morphologically processed foreground image to the computing unit 103 for the number and input of foreground pixels in the predetermined region according to the morphologically processed foreground image.
- the number of pixels in the predetermined area of the image is calculated as a congestion index.
- processing unit 105 is an optional component, indicated by the dashed box in FIG.
- FIG. 3 is a schematic structural diagram of a processing unit 105 according to an embodiment of the present invention. As shown in FIG. 3, the processing unit 105 includes:
- the first processing unit 301 is configured to expand a foreground pixel range in the foreground image according to a gap between the vehicles in the foreground image.
- the first processing unit 301 can also set the pixel value of the pixel in the gap between the vehicles to 1, that is, the pixel in the gap also serves as the foreground pixel, thereby expanding the range of the foreground pixel.
- the gap between the vehicles also occupies the road space, it has an impact on traffic congestion.
- the pixels in these gaps are not originally used as foreground pixels. Therefore, by expanding the pixels in the vehicle gap range to the foreground pixels, the accuracy of detection can be further improved.
- the congestion index is calculated according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, and accurate real-time detection can be performed, which is robust and has strong robustness. Noise tolerance.
- FIG. 4 is a schematic structural diagram of an electronic device according to Embodiment 2 of the present invention.
- the electronic device 400 includes a traffic congestion condition detecting device 401.
- the structure and function of the traffic congestion state detecting device 401 are the same as those in the first embodiment, and are not described herein again.
- Fig. 5 is a schematic block diagram showing the system configuration of an electronic apparatus according to a second embodiment of the present invention.
- electronic device 500 can include central processor 501 and memory 502; memory 502 is coupled to central processor 501.
- the figure is exemplary; other types of structures may be used in addition to or in place of the structure to implement telecommunications functions or other functions.
- the electronic device 500 may further include an input unit 503, a display 504, and a power source 505.
- the functions of the traffic congestion condition detecting apparatus described in Embodiment 1 may be integrated into the central processing unit 501.
- the central processing unit 501 may be configured to: extract a foreground image from the input image according to the background model; according to the foreground image, the number of foreground pixels in the predetermined area and the input image are The number of pixels in the predetermined area, a congestion index is calculated; and a traffic congestion condition is detected according to the congestion index.
- the central processing unit 501 is further configured to: correct the input image; and extract the foreground image from the input image according to the background model, including: extracting the foreground image from the corrected input image according to the background model.
- the correcting the input image comprises: correcting a graphic of a road in the input image.
- the central processing unit 501 is further configured to: perform morphological processing on the foreground image; the number of foreground pixels in the predetermined area according to the foreground image and pixels in the predetermined area of the input image
- the quantity, calculating the congestion index comprises: calculating a congestion index according to the number of foreground pixels in the predetermined area of the morphologically processed foreground image and the number of pixels of the input image in the predetermined area.
- the morphological processing of the foreground image comprises: expanding a foreground pixel range in the foreground image according to a gap between vehicles in the foreground image.
- the congestion index is a ratio of a number of foreground pixels of the foreground image in a predetermined area and a number of pixels of the input image in the predetermined area.
- the traffic congestion condition detecting apparatus described in Embodiment 1 may be configured separately from the central processing unit 501.
- the traffic congestion condition detecting apparatus may be configured as a chip connected to the central processing unit 501 through the central processing unit.
- the control of 501 implements the function of the traffic congestion condition detecting device.
- the electronic device 500 it is also not necessary for the electronic device 500 to include all of the components shown in FIG. 5 in this embodiment.
- central processor 501 can include a microprocessor or other processor device and/or logic device that receives input and controls various components of electronic device 500. Operation.
- Memory 502 can be one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable device.
- the central processing unit 501 can execute the program stored in the memory 502 to implement information storage or processing and the like.
- the functions of other components are similar to those of the existing ones and will not be described here.
- the various components of electronic device 500 may be implemented by special purpose hardware, firmware, software, or a combination thereof without departing from the scope of the invention.
- the congestion index is calculated according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, and accurate real-time detection can be performed, which is robust and has strong robustness. Noise tolerance.
- the embodiment of the present invention further provides a traffic congestion condition detecting method, which corresponds to the traffic congestion condition detecting apparatus of Embodiment 1.
- Fig. 6 is a flow chart showing a method of detecting a traffic congestion condition according to a third embodiment of the present invention. As shown in FIG. 6, the method includes:
- Step 601 Extract a foreground image from the input image according to the background model
- Step 602 Calculate a congestion index according to the number of foreground pixels in the predetermined area of the foreground image and the number of pixels of the input image in the predetermined area;
- Step 603 Detect a traffic congestion condition according to the congestion index.
- the method of extracting the foreground image, the method of calculating the congestion index, and the method of detecting the traffic congestion state according to the congestion index are the same as those in the first embodiment, and are not described herein again.
- the congestion index is calculated according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, and accurate real-time detection can be performed, which is robust and has strong robustness. Noise tolerance.
- the embodiment of the present invention further provides a traffic congestion condition detecting method, which corresponds to the traffic congestion condition detecting apparatus of Embodiment 1.
- Fig. 7 is a flow chart showing a method of detecting a traffic congestion condition according to a fourth embodiment of the present invention. As shown in FIG. 7, the method includes:
- Step 701 Perform correction on the input image.
- Step 702 Extract a foreground image from the corrected input image according to the background model
- Step 703 Perform morphological processing on the foreground image.
- Step 704 Calculate a congestion index according to the number of foreground pixels in the predetermined area of the morphologically processed foreground image and the number of pixels of the input image in the predetermined area;
- Step 705 Detect a traffic congestion condition according to the congestion index.
- a method of correcting an input image a method of extracting a foreground image, a method of performing a morphological operation on a foreground image, a method of calculating a congestion index, and a method of detecting a traffic congestion state according to the congestion index and Embodiment 1
- the records in the same are the same and will not be described here.
- the congestion index is calculated according to the number of foreground pixels of the foreground image in the predetermined area and the number of pixels of the input image, thereby detecting the traffic congestion condition, and accurate real-time detection can be performed, which is robust and has strong robustness. Noise tolerance.
- An embodiment of the present invention further provides a computer readable program, wherein when the traffic congestion condition detecting device or the electric When the program is executed in the child device, the program causes the computer to execute the traffic congestion condition detecting method described in Embodiment 3 or Embodiment 4 in the traffic congestion condition detecting device or the electronic device.
- the embodiment of the present invention further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to perform the traffic congestion described in Embodiment 3 or Embodiment 4 in a traffic congestion condition detecting device or an electronic device.
- Condition detection method
- the above apparatus and method of the present invention may be implemented by hardware or by hardware in combination with software.
- the present invention relates to a computer readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to cause the logic component to implement the various methods described above Or steps.
- the present invention also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, or the like.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
一种交通拥堵状况检测装置及方法。该装置包括：提取单元，用于根据背景模型从输入图像中提取前景图像；计算单元，用于根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数；检测单元，用于根据所述拥堵指数，检测交通拥堵状况。根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
Description
本发明涉及信息技术领域，特别涉及一种交通拥堵状况检测装置及方法。
随着城市的发展和生活水平的提高，车辆数量逐年增多，交通拥堵问题也日益突出。交通拥堵造成了各种资源的极大浪费并带来了严重的污染问题。对交通拥堵状况进行检测，从而交通管理部门能够及时了解交通拥堵状况并采取有效措施进行控制，因此是解决交通拥堵状况的重要手段之一。
在现有的方法中，通常采用边缘检测法和计数法来检测交通拥堵状况。其中，边缘检测法通过边缘像素的数量来检测拥堵状态，而计数法通过单位时间内通过监测区域的车辆数量来检测拥堵状态。
应该注意，上面对技术背景的介绍只是为了方便对本发明的技术方案进行清楚、完整的说明，并方便本领域技术人员的理解而阐述的。不能仅仅因为这些方案在本发明的背景技术部分进行了阐述而认为上述技术方案为本领域技术人员所公知。
发明内容
但是，发明人发现，采用现有的边缘检测法来检测交通拥堵状况时，由于不仅检测出车辆的边缘，还检测出道路的边缘，从而导致检测结果不准确，另外，该方法还需要根据时间和位置而频繁的调整参数；而采用现有的计数法来检测交通拥堵状况时，检测结果不准确。
本发明实施例提供一种交通拥堵状况检测装置及方法，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
根据本发明实施例的第一方面，提供一种交通拥堵状况检测装置，包括：提取单元，所述提取单元用于根据背景模型从输入图像中提取前景图像；计算单元，所述计算单元用于根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数；检测单元，所述检测单元用于根据所述拥堵
指数，检测交通拥堵状况
根据本发明实施例的第二方面，提供一种交通拥堵状况检测方法，包括：根据背景模型从输入图像中提取前景图像；根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数；根据所述拥堵指数，检测交通拥堵状况。
本发明实施例的有益效果在于，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
参照后文的说明和附图，详细公开了本发明的特定实施方式，指明了本发明的原理可以被采用的方式。应该理解，本发明的实施方式在范围上并不因而受到限制。在所附权利要求的条款的范围内，本发明的实施方式包括许多改变、修改和等同。
针对一种实施方式描述和/或示出的特征可以以相同或类似的方式在一个或更多个其它实施方式中使用，与其它实施方式中的特征相组合，或替代其它实施方式中的特征。
应该强调，术语“包括/包含”在本文使用时指特征、整件、步骤或组件的存在，但并不排除一个或更多个其它特征、整件、步骤或组件的存在或附加。
参照以下的附图可以更好地理解本发明的很多方面。附图中的部件不是成比例绘制的，而只是为了示出本发明的原理。为了便于示出和描述本发明的一些部分，附图中对应部分可能被放大或缩小。
在本发明的一个附图或一种实施方式中描述的元素和特征可以与一个或更多个其它附图或实施方式中示出的元素和特征相结合。此外，在附图中，类似的标号表示几个附图中对应的部件，并可用于指示多于一种实施方式中使用的对应部件。
图1是本发明实施例的交通拥堵状况检测装置的结构示意图；
图2是本发明实施例的校正单元104的结构示意图；
图3是本发明实施例的处理单元105的结构示意图；
图4是本发明实施例2的电子设备的结构示意图；
图5是本发明实施例2的电子设备的***构成的一示意框图；
图6是本发明实施例3的交通拥堵状况检测方法的流程图；
图7是本发明实施例4的交通拥堵状况检测方法的流程图。
参照附图，通过下面的说明书，本发明的前述以及其它特征将变得明显。在说明书和附图中，具体公开了本发明的特定实施方式，其表明了其中可以采用本发明的原则的部分实施方式，应了解的是，本发明不限于所描述的实施方式，相反，本发明包括落入所附权利要求的范围内的全部修改、变型以及等同物。
实施例1
本发明实施例提供一种交通拥堵状况检测装置。图1是本发明实施例的交通拥堵状况检测装置的结构示意图，如图1所示，该装置100包括：
提取单元101，用于根据背景模型从输入图像中提取前景图像；
计算单元102，用于根据前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量，计算拥堵指数；
检测单元103，用于根据该拥堵指数，检测交通拥堵状况。
由上述实施例可知，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
在本实施例中，输入图像可根据现有方法而获得。例如，该输入图像可通过提取监控视频中的某一帧图像而获得，例如该输入图像为当前帧。而该监控视频可通过安装在需要监测区域上方的摄像头而获得。
在本实施例中，该背景模型可使用能够检测移动缓慢或在一定时间内静止的物体的任何背景模型，本发明实施例不对具体的背景模型进行限制。
在本实施例中，提取单元101根据上述背景模型从输入图像中提取前景图像，例如，通过比较背景模型和输入图像，将明显不同的像素的像素值置为1，则该像素即为前景像素。
在本实施例中，前景图像可以是二值化图像，其中，前景像素的像素值为1，其余像素的像素值为0。
在本实施例中，在提取出前景图像之后，计算单元102根据前景图像在预定区域
中的前景像素数量和输入图像在该预定区域中的像素数量，计算拥堵指数。其中，该预定区域可根据实际需要而设置，例如，该预定区域为感兴趣区域(Region of Interest，ROI)。
在本实施例中，计算单元102可根据前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量之间的关系计算拥堵指数。例如，可根据前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量的各种比例关系来计算该拥堵指数。其中，像素数量可通过计数而获得。
例如，计算单元102可以根据以下的公式(1)计算拥堵指数：
J＝F/N (1)
其中，J表示拥堵指数，F表示前景图像在预定区域中的前景像素数量，N表示输入图像在该预定区域中的像素数量，F,N为正整数。
在本实施例中，在计算出拥堵指数之后，检测单元103根据该拥堵指数，检测交通拥堵状况。例如，可以根据拥堵指数J的数值与预定阈值的大小关系，判断当前的拥堵状况。其中，该预定阈值可根据实际需要而设置。
例如，当使用以上的公式(1)计算出拥堵指数J之后，该J的值为0～1之间，当该拥堵指数J大于0.8时，判断当前的交通为重度拥堵，当该拥堵指数J在0.6～0.8之间时，判断当前的交通为中度拥堵，当该拥堵指数J在0.4～0.6之间时，判断当前的交通为轻度拥堵，而当该拥堵指数J小于0.4时，则判断当前的交通为通畅。
在本实施例中，该装置100还可以包括：
校正单元104，用于对输入图像进行校正，并将校正后的图像提供给提取单元101，用于其根据背景模型从校正后的输入图像中提取前景图像。
在本实施例中，校正单元104为可选部件，在图1中用虚线框表示。
图2是本发明实施例的校正单元104的结构示意图，如图2所示，校正单元104包括：
第一校正单元201，用于对输入图像中的道路的图形进行校正。
在本实施例中，由于拍摄角度和距离的问题，输入图像中的道路的图像可能产生畸变，例如，原本为矩形的道路，由于拍摄角度的问题，在输入图像中可能表现为梯形。第一校正单元201将该梯形的道路图像校正为矩形。
这样，通过对输入图像的校正，能够进一步提高检测的准确度。
在本实施例中，该装置100还可以包括：
处理单元105，用于对前景图像进行形态学处理，并将经过形态学处理的前景图像提供给计算单元103，用于其根据经过形态学处理的前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量，计算拥堵指数。
在本实施例中，处理单元105为可选部件，在图1中用虚线框表示。
图3是本发明实施例的处理单元105的结构示意图，如图3所示，处理单元105包括：
第一处理单元301，用于根据前景图像中车辆之间的间隙，扩大该前景图像中的前景像素范围。
例如，第一处理单元301可将车辆之间的间隙中的像素的像素值也置为1，即将该间隙中的像素也作为前景像素，从而扩大了前景像素的范围。
这样，由于车辆之间的间隙也占用了道路空间，从而对交通拥堵产生影响。但是这些间隙范围内的像素原先并没有作为前景像素，因此，通过将车辆间隙范围内的像素也扩展为前景像素，能够进一步提高检测的准确度。
由上述实施例可知，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
实施例2
本发明实施例还提供了一种电子设备，图4是本发明实施例2的电子设备的结构示意图。如图4所示，电子设备400包括交通拥堵状况检测装置401，其中，交通拥堵状况检测装置401的结构和功能与实施例1中的记载相同，此处不再赘述。
图5是本发明实施例2的电子设备的***构成的一示意框图。如图5所示，电子设备500可以包括中央处理器501和存储器502；存储器502耦合到中央处理器501。该图是示例性的；还可以使用其它类型的结构，来补充或代替该结构，以实现电信功能或其它功能。
如图5所示，该电子设备500还可以包括：输入单元503、显示器504、电源505。
在一个实施方式中，实施例1所述的交通拥堵状况检测装置的功能可以被集成到中央处理器501中。其中，中央处理器501可以被配置为：根据背景模型从输入图像中提取前景图像；根据所述前景图像在预定区域中的前景像素数量和所述输入图像在
所述预定区域中的像素数量，计算拥堵指数；根据所述拥堵指数，检测交通拥堵状况。
其中，中央处理器501还可以被配置为：对输入图像进行校正；所述根据背景模型从输入图像中提取前景图像，包括：根据背景模型从校正后的输入图像中提取前景图像。
其中，所述对输入图像进行校正，包括：对输入图像中的道路的图形进行校正。
其中，中央处理器501还可以被配置为：对所述前景图像进行形态学处理；所述根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数，包括：根据经过形态学处理的前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数。
其中，所述对所述前景图像进行形态学处理，包括：根据所述前景图像中车辆之间的间隙，扩大所述前景图像中的前景像素范围。
其中，所述拥堵指数是所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量之比。
在另一个实施方式中，实施例1所述的交通拥堵状况检测装置可以与中央处理器501分开配置，例如可以将交通拥堵状况检测装置配置为与中央处理器501连接的芯片，通过中央处理器501的控制来实现交通拥堵状况检测装置的功能。
在本实施例中电子设备500也并不是必须要包括图5中所示的所有部件。
如图5所示，中央处理器501有时也称为控制器或操作控件，可以包括微处理器或其它处理器装置和/或逻辑装置，中央处理器501接收输入并控制电子设备500的各个部件的操作。
存储器502，例如可以是缓存器、闪存、硬驱、可移动介质、易失性存储器、非易失性存储器或其它合适装置中的一种或更多种。并且中央处理器501可执行该存储器502存储的该程序，以实现信息存储或处理等。其它部件的功能与现有类似，此处不再赘述。电子设备500的各部件可以通过专用硬件、固件、软件或其结合来实现，而不偏离本发明的范围。
由上述实施例可知，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
实施例3
本发明实施例还提供一种交通拥堵状况检测方法，其对应于实施例1的交通拥堵状况检测装置。图6是本发明实施例3的交通拥堵状况检测方法的流程图。如图6所示，该方法包括：
步骤601：根据背景模型从输入图像中提取前景图像；
步骤602：根据前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量，计算拥堵指数；
步骤603：根据该拥堵指数，检测交通拥堵状况。
在本实施例中，提取前景图像的方法、计算拥堵指数的方法以及根据该拥堵指数检测交通拥堵状况的方法与实施例1中的记载相同，此处不再赘述。
由上述实施例可知，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
实施例4
本发明实施例还提供一种交通拥堵状况检测方法，其对应于实施例1的交通拥堵状况检测装置。图7是本发明实施例4的交通拥堵状况检测方法的流程图。如图7所示，该方法包括：
步骤701：对输入图像进行校正；
步骤702：根据背景模型从校正后的输入图像中提取前景图像；
步骤703：对前景图像进行形态学处理；
步骤704：根据经过形态学处理的前景图像在预定区域中的前景像素数量和输入图像在该预定区域中的像素数量，计算拥堵指数；
步骤705：根据该拥堵指数，检测交通拥堵状况。
在本实施例中，对输入图像进行校正的方法、提取前景图像的方法、对前景图像进行形态学操作的方法、计算拥堵指数的方法以及根据该拥堵指数检测交通拥堵状况的方法与实施例1中的记载相同，此处不再赘述。
由上述实施例可知，根据预定区域中前景图像的前景像素数量和输入图像的像素数量来计算拥堵指数，从而检测交通拥堵状况，能够进行准确的实时检测，鲁棒性较好且具有较强的噪声容忍度。
本发明实施例还提供一种计算机可读程序，其中当在交通拥堵状况检测装置或电
子设备中执行所述程序时，所述程序使得计算机在所述交通拥堵状况检测装置或电子设备中执行实施例3或实施例4所述的交通拥堵状况检测方法。
本发明实施例还提供一种存储有计算机可读程序的存储介质，其中所述计算机可读程序使得计算机在交通拥堵状况检测装置或电子设备中执行实施例3或实施例4所述的交通拥堵状况检测方法。
本发明以上的装置和方法可以由硬件实现，也可以由硬件结合软件实现。本发明涉及这样的计算机可读程序，当该程序被逻辑部件所执行时，能够使该逻辑部件实现上文所述的装置或构成部件，或使该逻辑部件实现上文所述的各种方法或步骤。本发明还涉及用于存储以上程序的存储介质，如硬盘、磁盘、光盘、DVD、flash存储器等。
以上结合具体的实施方式对本发明进行了描述，但本领域技术人员应该清楚，这些描述都是示例性的，并不是对本发明保护范围的限制。本领域技术人员可以根据本发明的精神和原理对本发明做出各种变型和修改，这些变型和修改也在本发明的范围内。
Claims (12)
- 一种交通拥堵状况检测装置，包括：提取单元，所述提取单元用于根据背景模型从输入图像中提取前景图像；计算单元，所述计算单元用于根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数；检测单元，所述检测单元用于根据所述拥堵指数，检测交通拥堵状况。
- 根据权利要求1所述的装置，其中，所述装置还包括：校正单元，所述校正单元用于对输入图像进行校正；所述提取单元用于根据背景模型从校正后的输入图像中提取前景图像。
- 根据权利要求2所述的装置，其中，所述校正单元包括：第一校正单元，所述第一校正单元用于对输入图像中的道路的图形进行校正。
- 根据权利要求1所述的装置，其中，所述装置还包括：处理单元，所述处理单元用于对所述前景图像进行形态学处理；所述计算单元用于根据经过形态学处理的前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数。
- 根据权利要求4所述的装置，其中，所述处理单元包括：第一处理单元，所述第一处理单元用于根据所述前景图像中车辆之间的间隙，扩大所述前景图像中的前景像素范围。
- 根据权利要求1所述的装置，其中，所述拥堵指数是所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量之比。
- 一种交通拥堵状况检测方法，包括：根据背景模型从输入图像中提取前景图像；根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数；根据所述拥堵指数，检测交通拥堵状况。
- 根据权利要求7所述的方法，其中，所述方法还包括：对输入图像进行校正；所述根据背景模型从输入图像中提取前景图像，包括：根据背景模型从校正后的输入图像中提取前景图像。
- 根据权利要求8所述的方法，其中，所述对输入图像进行校正，包括：对输入图像中的道路的图形进行校正。
- 根据权利要求7所述的方法，其中，所述方法还包括：对所述前景图像进行形态学处理；所述根据所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数，包括：根据经过形态学处理的前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量，计算拥堵指数。
- 根据权利要求10所述的方法，其中，所述对所述前景图像进行形态学处理，包括：根据所述前景图像中车辆之间的间隙，扩大所述前景图像中的前景像素范围。
- 根据权利要求7所述的方法，其中，所述拥堵指数是所述前景图像在预定区域中的前景像素数量和所述输入图像在所述预定区域中的像素数量之比。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/086967 WO2017028012A1 (zh) | 2015-08-14 | 2015-08-14 | 交通拥堵状况检测装置及方法 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/086967 WO2017028012A1 (zh) | 2015-08-14 | 2015-08-14 | 交通拥堵状况检测装置及方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017028012A1 true WO2017028012A1 (zh) | 2017-02-23 |
Family
ID=58050444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/086967 WO2017028012A1 (zh) | 2015-08-14 | 2015-08-14 | 交通拥堵状况检测装置及方法 |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2017028012A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782659A (zh) * | 2019-09-09 | 2020-02-11 | 腾讯科技（深圳）有限公司 | 路况确定方法、装置、服务器及存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556739A (zh) * | 2009-05-14 | 2009-10-14 | 浙江大学 | 基于本征图像分解的车辆检测算法 |
| CN101714296A (zh) * | 2009-11-13 | 2010-05-26 | 北京工业大学 | 一种基于伸缩窗的实时动态交通拥堵检测方法 |
| CN101729872A (zh) * | 2009-12-11 | 2010-06-09 | 南京城际在线信息技术有限公司 | 一种基于视频监控图像自动判别道路交通状态的方法 |
| CN102136195A (zh) * | 2011-03-28 | 2011-07-27 | 长安大学 | 一种基于图像纹理检测道路交通状况的方法 |
-
2015
- 2015-08-14 WO PCT/CN2015/086967 patent/WO2017028012A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556739A (zh) * | 2009-05-14 | 2009-10-14 | 浙江大学 | 基于本征图像分解的车辆检测算法 |
| CN101714296A (zh) * | 2009-11-13 | 2010-05-26 | 北京工业大学 | 一种基于伸缩窗的实时动态交通拥堵检测方法 |
| CN101729872A (zh) * | 2009-12-11 | 2010-06-09 | 南京城际在线信息技术有限公司 | 一种基于视频监控图像自动判别道路交通状态的方法 |
| CN102136195A (zh) * | 2011-03-28 | 2011-07-27 | 长安大学 | 一种基于图像纹理检测道路交通状况的方法 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782659A (zh) * | 2019-09-09 | 2020-02-11 | 腾讯科技（深圳）有限公司 | 路况确定方法、装置、服务器及存储介质 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10212397B2 (en) | Abandoned object detection apparatus and method and system | |
| US20170032669A1 (en) | Apparatus and method for controlling traffic lights of a crossing | |
| TW202011733A (zh) | 對影像進行目標取樣的方法及裝置 | |
| US9870510B2 (en) | Apparatus and method for counting moving objects | |
| WO2021082922A1 (zh) | 一种检测屏幕显示断线的方法及设备 | |
| US20130120125A1 (en) | Method and system for lane departure warning | |
| US10936876B2 (en) | Content recognition method, system and storage medium thereof | |
| US8908915B2 (en) | Devices and methods for tracking moving objects | |
| US20170109892A1 (en) | Method and apparatus for detecting a traffic state and electronic equipment | |
| US20170103536A1 (en) | Counting apparatus and method for moving objects | |
| WO2017206444A1 (zh) | 一种成像差异检测方法、装置及计算机存储介质 | |
| US20190311492A1 (en) | Image foreground detection apparatus and method and electronic device | |
| US11017552B2 (en) | Measurement method and apparatus | |
| KR102006763B1 (ko) | Cctv 영상을 이용한 도로 혼잡도 분석 방법 및 시스템 | |
| KR20170032033A (ko) | 전경 추출 방법 및 장치 | |
| JP2016162420A (ja) | 注目領域検出装置、注目領域検出方法及びプログラム | |
| JP2013004089A (ja) | 画像処理方法、画像処理装置及びスキャナ | |
| CN112733703A (zh) | 一种车辆停放状态检测方法及*** | |
| WO2017028047A1 (zh) | 背景模型的提取方法、装置以及图像处理设备 | |
| TW201501080A (zh) | 目標偵測與追蹤方法及系統 | |
| Yang et al. | Practical homography-based perspective correction method for license plate recognition | |
| US10965858B2 (en) | Image processing apparatus, control method thereof, and non-transitory computer-readable storage medium for detecting moving object in captured image | |
| CN105554414A (zh) | 强光抑制方法及装置 | |
| WO2018058573A1 (zh) | 对象检测方法、对象检测装置以及电子设备 | |
| WO2017028012A1 (zh) | 交通拥堵状况检测装置及方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15901218 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 15901218 Country of ref document: EP Kind code of ref document: A1 |